Bayesian logistic mixed-effects modelling of transect data: relating red tree coral presence to habitat characteristics
Bayesian logistic mixed-effects modelling of transect data: relating red tree coral presence to habitat characteristics
复制标题
DOI：
10.1093/icesjms/fsv163
复制
发表时间：
2015-11
影响因子：
3.3
通讯作者：
M. Masuda;R. Stone
中科院分区：
文献类型：
--
作者：
M. Masuda;R. Stone
收集关于样带的连续数据是生境和渔业资源评估的一种常见做法;然而，标准回归模型假设对序列相关数据是独立的，其应用是有问题的。我们如何利用广义线性混合模型（GLMM），即纵向数据的广义线性模型，通常用于随时间进行的研究的方法也可以应用于其他类型的聚类或序列相关数据。我们将特定的GLMM应用于纵向数据，一个分层贝叶斯逻辑混合效应模型（BLMM），从潜水视频记录的海底断面在阿拉斯加湾的两个网站获得的海洋生态数据集。BLMM有效地将红树珊瑚（Primnoa pacifica;即二元数据）的存在与生境特征联系起来：红树珊瑚的存在与作为主要基质的基岩（估计比值比9-19）、高至非常高的海底粗糙度（估计比值比3-5）和中至高坡度（估计比值比2-3）高度相关。在研究中心，协变量深度不太重要。我们还演示和比较两种方法的模型检查：充分和混合后验预测评估，后者提供了更现实的评估，我们计算的方差分配系数报告的层次模型的多个层次解释的变化。
The collection of continuous data on transects is a commonpractice in habitat and fishery stock assessments; however, the application of standard regressionmodels that assume independence to serially correlateddata is problematic.Weshow that generalized linearmixedmodels (GLMMs), i.e. generalized linear models for longitudinal data, that are normally used for studies performed over time can also be applied to other types of clustered or serially correlated data.We apply a specific GLMM for longitudinal data, a hierarchical Bayesian logisticmixed-effectsmodel (BLMM), to a marine ecology dataset obtained from submersible video recordings of the seabed on transects at two sites in the Gulf of Alaska. The BLMMwas effective in relating the presence of red tree corals (Primnoa pacifica; i.e. binary data) to habitat characteristics: the presence of red tree corals is highly associated with bedrock as the primary substrate (estimated odds ratio 9–19), high to very high seabed roughness (estimated odds ratio 3–5), and medium to high slope (estimated odds ratio 2–3). The covariate depth was less important at the sites. We also demonstrate and compare twomethods ofmodel checking: full andmixed posterior predictive assessments, the latter ofwhich provided amore realistic assessment, and we calculate the variance partition coefficient for reporting the variation explained by multiple levels of the hierarchical model.